© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 8616
    Prev
    Next
    INDEX
    Explanations

    strings, vibrations, and sounds

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    데이
    1.77
    ில்
    1.70
    ရှား
    1.69
    𝘆
    1.67
    ுள்ளார்
    1.63
     জনের
    1.62
    s
    1.55
    }$
    1.52
    கிறது
    1.52
    ्स
    1.52
    POSITIVE LOGITS
          
    1.34
    ש
    1.30
    <unused2188>
    1.26
    ت
    1.23
    cents
    1.21
    ーーーー
    1.20
    sofar
    1.17
    confirm
    1.16
     जितना
    1.16
    тят
    1.16
    Activations Density 0.000%

    No Known Activations